BERT, can HE predict contrastive focus? Predicting and controlling prominence in neural TTS using a language model. (arXiv:2207.01718v1 [cs.CL])

Several recent studies have tested the use of transformer language model
representations to infer prosodic features for text-to-speech synthesis (TTS).
While these studies have explored prosody in general, in this work, we look
specifically at the prediction of contrastive focus on personal pronouns. This
is a particularly challenging task as it often requires semantic, discursive
and/or pragmatic knowledge to predict correctly. We collect a corpus of
utterances containing contrastive focus and we evaluate the accuracy of a BERT
model, finetuned …

arxiv bert language language model tts